Triple
T24807678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cappadocians |
E620696
|
entity |
| Predicate | transitionedUnder |
P85323
|
FINISHED |
| Object | Roman annexation of Cappadocia |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Roman annexation of Cappadocia | Statement: [Cappadocians, transitionedUnder, Roman annexation of Cappadocia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transitionedUnder Context triple: [Cappadocians, transitionedUnder, Roman annexation of Cappadocia]
-
A.
transitionedThrough
Indicates that an entity passed from one state, phase, or condition to another by way of an intermediate state, phase, or condition.
-
B.
transitionedInto
Indicates that one entity changed state, form, role, or condition to become another specified state or entity.
-
C.
transferredUnder
Indicates that something is moved, conveyed, or reassigned from one party, context, or control to another under specified terms or conditions.
-
D.
changedUnder
Indicates that one entity has undergone alteration, modification, or transformation as a result of the influence, action, or conditions imposed by another entity.
-
E.
cededUnder
chosen
Indicates that control, ownership, or rights over something are transferred from one party to another under specified terms or conditions.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e2fabf26bc8190b191faac8f67065b |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f55e519978819087a1676564a74630 |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 18, 2026, 4:50 a.m.